Python tushare.get_stock_basics() Examples

def QA_save_stock_day_all(client=DATABASE):
    df = ts.get_stock_basics()
    __coll = client.stock_day
    __coll.ensure_index('code')

    def saving_work(i):
        QA_util_log_info('Now Saving ==== %s' % (i))
        try:
            data_json = QA_fetch_get_stock_day(i, start='1990-01-01')

            __coll.insert_many(data_json)
        except Exception as e:
            print(e)
            QA_util_log_info('error in saving ==== %s' % str(i))

    for i_ in range(len(df.index)):
        QA_util_log_info('The %s of Total %s' % (i_, len(df.index)))
        QA_util_log_info(
            'DOWNLOAD PROGRESS %s ' %
            str(float(i_ / len(df.index) * 100))[0:4] + '%'
        )
        saving_work(df.index[i_])

    saving_work('hs300')
    saving_work('sz50') 

def stock_select_to_sql(PE,TotalAssists):
    create_stock_select_table()    
    
    df=ts.get_stock_basics()
    #df.to_excel('c:/python/all_stock_list.xlsx')
    df= df[df['pe'] < PE]
    df= df[df['pe'] > 0]
    print(df)
    #df.to_excel('c:/python/all_stock_pe50.xlsx')
    df= df[df['totalAssets'] >= TotalAssists]
    df= df[df['rev'] >= 0]
    df= df[df['profit'] >= 0]
    #df.to_excel('c:/python/all_stock_assets100.xlsx')
    print(df)  
    print('...........................before')
    #df=df.iloc[1:]
    #df.to_excel('c:/python/all_stock_assets100head.xlsx')
    #sql.df_to_mysql('all_stock_select',df)
    df_to_mysql('all_stock_select',df)
    print('...........................after') 

def __init__(self):
        super().__init__()
        self.frequence = FREQUENCE.DAY
        self.market_type = MARKET_TYPE.STOCK_CN

        # self.stock_basics = QATs.get_stock_basics()
        # self.time_to_Market_300439 = self.stock_basics.loc['300439', 'timeToMarket']
        # self.time_to_Market_300439 = QA.QA_util_date_int2str(self.time_to_Market_300439)
        # self.time_to_day = QA_util_datetime_to_strdate(QA.QA_util_date_today())
        # print(self.time_to_Market_300439)
        # print(self.time_to_day)

        self.time_to_Market_300439 = '2015-04-22'
        self.time_to_day = '2018-05-01'

        self.df_from_Tdx = QA_fetch_stock_day(
            '300439', self.time_to_Market_300439, self.time_to_day, 'pd')
        # print(self.df_from_Tdx)

        self.ma05 = QA_indicator_MA(self.df_from_Tdx, 5)

        self.ma10 = QA_indicator_MA(self.df_from_Tdx, 10)
        self.ma15 = QA_indicator_MA(self.df_from_Tdx, 15)
        self.ma20 = QA_indicator_MA(self.df_from_Tdx, 20)
        # print(self.df5) 

def run_daybacktest(self):
        #import QUANTAXIS as QA
        # print(QA.QA_fetch_stock_block_adv().code[0:5])
        # self.stock_basics = QATs.get_stock_basics()
        # self.time_to_Market_300439 = self.stock_basics.loc['300439', 'timeToMarket']
        # self.time_to_Market_300439 = QA.QA_util_date_int2str(self.time_to_Market_300439)
        # self.time_to_day = QA_util_datetime_to_strdate(QA.QA_util_date_today())
        # print(self.time_to_Market_300439)
        # print(self.time_to_day)
        # QA.QA_util_time_now()

        self.time_to_Market_300439 = '2015-04-22'
        self.time_to_day = '2018-05-01'

        backtest = Backtest(market_type=MARKET_TYPE.STOCK_CN,
                            frequence=FREQUENCE.DAY,
                            start=self.time_to_Market_300439,
                            end=self.time_to_day,
                            code_list=['300439'],
                            commission_fee=0.00015)
        backtest.start_market()

        backtest.run()
        backtest.stop()
        print("结束回测！") 

def processing_sector_cashflow_count(root_path, symbols, dates):
    stock_info = ts.get_stock_basics()

    sector_columns = list(set(stock_info['industry'].values.tolist()))

    sector_count = pd.DataFrame(columns=sector_columns, index=dates)
    sector_count.index.name = 'date'
    sector_count = sector_count.fillna(0)

    pbar = tqdm(total=len(symbols))

    for symbol in symbols:
        startTime = time.time()
        out_file = root_path + "/Data/CSV/cashflow/" + symbol + ".csv"
        column = stock_info[stock_info.index == symbol]["industry"][0]

        if os.path.exists(out_file) == False:
            pbar.update(1)
            #print(symbol, column)
            continue
        
        df_symbol = pd.read_csv(out_file, index_col=["date"])
        df = df_symbol['buy_amount'] - df_symbol["sell_amount"]
        sector_count[column] = sector_count[column].add(df, fill_value=0)

        outMessage = '%-*s processed in:  %.4s seconds' % (6, symbol, (time.time() - startTime))
        pbar.set_description(outMessage)
        pbar.update(1)

    pbar.close()

    sector_count = sector_count.sort_index(ascending=False)
    sector_count.to_csv("cashflow_sector.csv") 

def download_stock_basic_info():
    """
    获取股票基本信息
    :return:
    """
    
    try:
        df = ts.get_stock_basics()

        print(df.columns)
        df['code'] = df.index

        print(df.head())
        if len(df):
            engine = db.get_w_engine()
            to_sql(STOCK_BASIC_TABLE, engine, df, type='replace')
            # df.to_sql(STOCK_BASIC_TABLE, engine, if_exists='append', index=False)

        # 添加指数
        indexs = [('sh', '上证指数', '指数','全国','19910715'),
                  ('sz', '深圳成指', '指数','全国','19940720'),
                  ('hs300', '沪深300指数', '指数','全国','20050408'),
                  ('sz50', '上证50指数', '指数','全国','20040102'),
                  ('zxb', '中小板指数', '指数','全国','20050607'),
                  ('cyb', '创业板指数', '指数','全国','20100531'),]
        df = pd.DataFrame(indexs, columns=[KEY_CODE,KEY_NAME, KEY_INDUSTRY, KEY_AREA, KEY_TimeToMarket])
        print(df)
        to_sql(STOCK_BASIC_TABLE, engine, df, type='replace')

           
    except Exception as e:
        print(str(e))

# 获取所有股票的历史K线 

def basic_info():
    '''
    获取股票列表
    '''
    return ts.get_stock_basics() 

def industry_stat(industry):    
    df = pd.DataFrame(ts.get_stock_basics().values,columns = ts.get_stock_basics().columns)   
    pe_stat = df[df.industry == industry].drop(['name','industry','area'], axis = 1).astype('float')
# =============================================================================
#     print(pe_stat.dtypes)
# =============================================================================
    result_df = pe_stat.describe()
    print(result_df)
    return result_df




#作用：查看行业平均值统计
#输出：所有行业平均统计数(筛选条件:PE <100,pb <10,1000>rev>-1000,1000>profit>-1000,,1000>gpr>-1000,,1000>npr>-1000) 

def Estimation(): 
               
    result_df = pd.DataFrame(ts.get_stock_basics().values,columns = ts.get_stock_basics().columns)
    df_to_mysql('industry_estimation_detail',result_df)
    
    return result_df




#作用：查看行业平均值统计
#输入：行业名称
#输出：行业平均统计数 

def Get_all_industry_average_data():
    a = ts.get_stock_basics()
    for i in range(0,len(a)):
        print('industry:',a.iloc[i,1])
        test=Estimation(dbconn,a.iloc[i,1],2017)
# App示例代码，用完删掉


#Estimation(dbconn,'家电行业')
#print(GetIndustryName('福耀玻璃')) 
#CreateTable()
#Estimation(dbconn,GetIndustryName('宁沪高速'),2017)  
#Estimation(dbconn,GetIndustryName('格力电器'),2017)   
#Estimation(dbconn,GetIndustryName('福耀玻璃'),2017)   
#Estimation(dbconn,GetIndustryName('隆基股份'),2017)   

#def get_interest_list():
#    '''
#    解析"感兴趣的个股列表.txt",返回list类型的数据供其他模块使用
#    '''
#    list_id = []
#    with open('../SQL/感兴趣的个股列表.txt','r') as fh:
#        s = fh.readline()   #获取更新时间
#        s = fh.readline()   #获取目标长度  
#        
#        lines = fh.readlines()  #获取目标内容
#    for s in lines:
#        code = s[:6]
#        list_id.append(code)    
#    list_id.sort()
#    return list_id  
#
#for s in get_interest_list():
#    Estimation(dbconn,GetIndustryName(s),2017) 

def calcu_all_stocks_3year_roe_and_average_profit(year):  # 生成3年平均利润列表
    path = os.path.join(current_folder, 'stock_list%s.csv' % today)
    if not os.path.exists(path):
        data = ts.get_stock_basics()
        lie = [
            '名字', '行业', '地区', '市盈率', '流通股本', '总股本', '总资产(万)', '流动资产', '固定资产',
            '公积金', '每股公积金', '每股收益', '每股净资', '市净率', '上市日期', '未分利润', '每股未分配',
            '收入同比(%)', '利润同比(%)', '毛利率(%)', '净利润率(%)', '股东人数'
        ]
        data.columns = lie
        data.index.names = ['代码']
        data = data[data['上市日期'] < three_year_ago()]  # 排除上市不满3年的公司
        data.to_csv(path, encoding='utf-8')

    data = pd.read_csv(path, encoding='utf-8', index_col=0)
    # print(data)
    data['平均利润'] = 0
    for index, row in data.iterrows():
        try:
            data.loc[index, '平均利润'] = calcu_3year_average_profit(
                '%06d' % index, year)
        except Exception as e:
            print(e)
            data.loc[index, '平均利润'] = 0

        data.loc[index, '上4年roe'], data.loc[index, '上3年roe'], data.loc[index, '上2年roe'], \
        data.loc[index, '上1年roe'], data.loc[index, '当年roe'] = last_5_year_roe('%06d' % index, year)
        print('完成%s' % index)
    data.to_csv(
        os.path.join(current_folder, '3年平均利润及其他财务指标%s.csv' % today),
        encoding='utf-8') 

def getStockBasicFromTushare(self,dbName,colName):
		db = self._Conn[dbName]
		collection = db.get_collection(colName)
		stock_basic_info = ts.get_stock_basics()
		for i in range(len(stock_basic_info)):
			data = {stock_basic_info.index.name : stock_basic_info.index[i]}
			data.update({'name' : stock_basic_info['name'][i]})
			data.update({'industry' : stock_basic_info['industry'][i]})
			data.update({'area' : stock_basic_info['area'][i]})
			data.update({'pe' : stock_basic_info['pe'][i]})
			data.update({'outstanding' : stock_basic_info['outstanding'][i]})
			data.update({'totals' : stock_basic_info['totals'][i]})
			data.update({'totalAssets' : stock_basic_info['totalAssets'][i]})
			data.update({'liquidAssets' : stock_basic_info['liquidAssets'][i]})
			data.update({'fixedAssets' : stock_basic_info['fixedAssets'][i]})
			data.update({'reserved' : stock_basic_info['reserved'][i]})
			data.update({'reservedPerShare' : stock_basic_info['reservedPerShare'][i]})
			data.update({'esp' : stock_basic_info['esp'][i]})
			data.update({'bvps' : stock_basic_info['bvps'][i]})
			data.update({'pb' : stock_basic_info['pb'][i]})
			data.update({'undp' : stock_basic_info['undp'][i]})
			data.update({'perundp' : stock_basic_info['perundp'][i]})
			data.update({'rev' : stock_basic_info['rev'][i]})
			data.update({'profit' : stock_basic_info['profit'][i]})
			data.update({'gpr' : stock_basic_info['gpr'][i]})
			data.update({'npr' : stock_basic_info['npr'][i]})
			data.update({'holders' : stock_basic_info['holders'][i]})
			#detail = dict(zip(stock_basic_info.columns, [stock_basic_info[j][i] for j in stock_basic_info.columns]))
			collection.insert_one(data) 

def QA_fetch_get_stock_info(name):
    data = ts.get_stock_basics()
    try:
        return data if name == '' else data.loc[name]
    except:
        return None 

def QA_save_stock_day_with_fqfactor(client=DATABASE):
    df = ts.get_stock_basics()

    __coll = client.stock_day
    __coll.ensure_index('code')

    def saving_work(i):
        QA_util_log_info('Now Saving ==== %s' % (i))
        try:
            data_hfq = QA_fetch_get_stock_day(
                i,
                start='1990-01-01',
                if_fq='02',
                type_='pd'
            )
            data_json = QA_util_to_json_from_pandas(data_hfq)
            __coll.insert_many(data_json)
        except Exception as e:
            print(e)
            QA_util_log_info('error in saving ==== %s' % str(i))

    for i_ in range(len(df.index)):
        QA_util_log_info('The %s of Total %s' % (i_, len(df.index)))
        QA_util_log_info(
            'DOWNLOAD PROGRESS %s ' %
            str(float(i_ / len(df.index) * 100))[0:4] + '%'
        )
        saving_work(df.index[i_])

    saving_work('hs300')
    saving_work('sz50')

    QA_util_log_info('Saving Process has been done !')
    return 0 

def QA_save_stock_day_all_bfq(client=DATABASE):
    df = ts.get_stock_basics()

    __coll = client.stock_day_bfq
    __coll.ensure_index('code')

    def saving_work(i):
        QA_util_log_info('Now Saving ==== %s' % (i))
        try:
            df = QA_fetch_get_stock_day(i, start='1990-01-01', if_fq='bfq')

            __coll.insert_many(json.loads(df.to_json(orient='records')))
        except Exception as e:
            print(e)
            QA_util_log_info('error in saving ==== %s' % str(i))

    for i_ in range(len(df.index)):
        QA_util_log_info('The %s of Total %s' % (i_, len(df.index)))
        QA_util_log_info(
            'DOWNLOAD PROGRESS %s ' %
            str(float(i_ / len(df.index) * 100))[0:4] + '%'
        )
        saving_work(df.index[i_])

    saving_work('hs300')
    saving_work('sz50') 

def QA_SU_save_stock_info_tushare(client=DATABASE):
    '''
        获取 股票的 基本信息，包含股票的如下信息

        code,代码
        name,名称
        industry,所属行业
        area,地区
        pe,市盈率
        outstanding,流通股本(亿)
        totals,总股本(亿)
        totalAssets,总资产(万)
        liquidAssets,流动资产
        fixedAssets,固定资产
        reserved,公积金
        reservedPerShare,每股公积金
        esp,每股收益
        bvps,每股净资
        pb,市净率
        timeToMarket,上市日期
        undp,未分利润
        perundp, 每股未分配
        rev,收入同比(%)
        profit,利润同比(%)
        gpr,毛利率(%)
        npr,净利润率(%)
        holders,股东人数

        add by tauruswang

    在命令行工具 quantaxis 中输入 save stock_info_tushare 中的命令
    :param client:
    :return:
    '''
    df = QATs.get_stock_basics()
    print(" Get stock info from tushare,stock count is %d" % len(df))
    coll = client.stock_info_tushare
    client.drop_collection(coll)
    json_data = json.loads(df.reset_index().to_json(orient='records'))
    coll.insert(json_data)
    print(" Save data to stock_info_tushare collection， OK") 

def getStocksList_CHN(root_path):
    try:
        df = queryStockList(root_path, "DB_STOCK", "SHEET_CHN")
        df.index = df.index.astype(str).str.zfill(6)
    except Exception as e:
        df = pd.DataFrame()

    if df.empty == False: return df
    
    stock_info = ts.get_stock_basics()
    listData = pd.DataFrame(stock_info)
    listData['daily_update'] = '1970-07-01'
    listData['weekly_update'] = '1970-07-01'
    listData['monthly_update'] = '1970-07-01'
    listData['news_update'] = '1970-07-01'
    listData.index.name = 'symbol'
    listData = listData.reset_index()

    #listData.index.name = 'symbol'
    #listData.index = listData.index.astype(str).str.zfill(6) #[str(symbol).zfill(6) for symbol in listData.index] #listData.index.astype(str).str.zfill(6)
    #print(listData.index)
    #listData['symbol'] = listData['symbol'].str.strip()

    storeStockList(root_path, "DB_STOCK", "SHEET_CHN", listData)
    df = queryStockList(root_path, "DB_STOCK", "SHEET_CHN")

    if df.empty == False: df.index = df.index.astype(str).str.zfill(6)
    return df 

def __init__(self,save=True):
        """
        code,代码
        name,名称
        industry,所属行业
        area,地区
        pe,市盈率
        outstanding,流通股本(亿)
        totals,总股本(亿)
        totalAssets,总资产(万)
        liquidAssets,流动资产
        fixedAssets,固定资产
        reserved,公积金
        reservedPerShare,每股公积金
        esp,每股收益
        bvps,每股净资
        pb,市净率
        timeToMarket,上市日期
        undp,未分利润
        perundp, 每股未分配
        rev,收入同比(%)
        profit,利润同比(%)
        gpr,毛利率(%)
        npr,净利润率(%)
        holders,股东人数
        datatime:获取数据日期
        datatimestramp:获取数据时间戳
        """
        
        try:
            stockBasics = ts.get_stock_basics()
        except:
            stockBasics  = None
            
        if  stockBasics  is not None:
            now = dt.datetime.now()
            stockBasics['datatime'] = now.strftime('%Y-%m-%d')
            stockBasics['datatimestramp'] = now.strftime('%H:%M:%S')
            stockBasics['code'] = stockBasics.index
            indexlist = ['code','datatime']##数据库索引
            tableName = 'SymbolMdm'
            print self.__name__
            database(stockBasics,indexlist,tableName,save) 

def stat_all(tmp_datetime):
    # 存款利率
    data = ts.get_deposit_rate()
    common.insert_db(data, "ts_deposit_rate", False, "`date`,`deposit_type`")

    # 贷款利率
    data = ts.get_loan_rate()
    common.insert_db(data, "ts_loan_rate", False, "`date`,`loan_type`")

    # 存款准备金率
    data = ts.get_rrr()
    common.insert_db(data, "ts_rrr", False, "`date`")

    # 货币供应量
    data = ts.get_money_supply()
    common.insert_db(data, "ts_money_supply", False, "`month`")

    # 货币供应量(年底余额)
    data = ts.get_money_supply_bal()
    common.insert_db(data, "ts_money_supply_bal", False, "`year`")

    # 国内生产总值(年度)
    data = ts.get_gdp_year()
    common.insert_db(data, "ts_gdp_year", False, "`year`")

    # 国内生产总值(季度)
    data = ts.get_gdp_quarter()
    common.insert_db(data, "ts_get_gdp_quarter", False, "`quarter`")

    # 三大需求对GDP贡献
    data = ts.get_gdp_for()
    common.insert_db(data, "ts_gdp_for", False, "`year`")

    # 三大产业对GDP拉动
    data = ts.get_gdp_pull()
    common.insert_db(data, "ts_gdp_pull", False, "`year`")

    # 三大产业贡献率
    data = ts.get_gdp_contrib()
    common.insert_db(data, "ts_gdp_contrib", False, "`year`")

    # 居民消费价格指数
    data = ts.get_cpi()
    common.insert_db(data, "ts_cpi", False, "`month`")

    # 工业品出厂价格指数
    data = ts.get_ppi()
    common.insert_db(data, "ts_ppi", False, "`month`")

    #############################基本面数据 http://tushare.org/fundamental.html
    # 股票列表
    data = ts.get_stock_basics()
    print(data.index)
    common.insert_db(data, "ts_stock_basics", True, "`code`")


# 创建新数据库。